Related papers: HATS: High-Accuracy Triple-Set Watermarking for La…

We propose a high-payload image watermarking method for textual embedding, where a semantic description of the image - which may also correspond to the input text prompt-, is embedded inside the image. In order to be able to robustly embed…

Deep image watermarking, which refers to enabling imperceptible watermark embedding and reliable extraction in cover images, has been shown to be effective for copyright protection of image assets. However, existing methods face limitations…

We study the problem of multi-bit watermarking for large language models (LLMs). We introduce a block-autoregressive model inspired by multi-token prediction, in which the encoder has limited non-causal access to token distributions within…

With the rapid growth of Large Language Models (LLMs), safeguarding textual content against unauthorized use is crucial. Watermarking offers a vital solution, protecting both - LLM-generated and plain text sources. This paper presents a…

The radioactive nature of Large Language Model (LLM) watermarking enables the detection of watermarks inherited by student models when trained on the outputs of watermarked teacher models, making it a promising tool for preventing…

Large Language Model (LLM) watermarking embeds detectable signals into generated text for copyright protection, misuse prevention, and content detection. While prior studies evaluate robustness using watermark removal attacks, these methods…

Large language model (LLM) unlearning is critical in real-world applications where it is necessary to efficiently remove the influence of private, copyrighted, or harmful data from some users. Existing utility-centric unlearning metrics…

As large language models (LLMs) become increasingly commonplace, concern about distinguishing between human and AI text increases as well. The growing power of these models is of particular concern to teachers, who may worry that students…

Autoregressive (AR) image generation models have gained increasing attention for their breakthroughs in synthesis quality, highlighting the need for robust watermarking to prevent misuse. However, existing in-generation watermarking…

A recent and exciting thread of work focuses on developing methods for watermarking the output of large language models (LLMs). We focus on provably undetectable watermarking-that is, schemes that do not alter the output distribution of the…

Watermarking is an effective way to trace model-generated content. Current watermark methods cannot resist forgery attacks, such as a deceptive claim that the model-generated content is a response to a fabricated prompt. None of them can be…

Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable to structural perturbations, such as sentence splitting and…

As large language models (LLMs) continue to advance rapidly, reliable governance tools have become critical. Publicly verifiable watermarking is particularly essential for fostering a trustworthy AI ecosystem. A central challenge persists:…

Securing digital text is becoming increasingly relevant due to the widespread use of large language models. Individuals' fear of losing control over data when it is being used to train such machine learning models or when distinguishing…

Watermarking for large language models (LLMs) has emerged as an effective tool for distinguishing AI-generated text from human-written content. Statistically, watermark schemes induce dependence between generated tokens and a pseudo-random…

Amidst rising concerns about the internet being proliferated with content generated from language models (LMs), watermarking is seen as a principled way to certify whether text was generated from a model. Many recent watermarking techniques…

Large Language Models (LLMs) are widely used in complex natural language processing tasks but raise privacy and security concerns due to the lack of identity recognition. This paper proposes a multi-party credible watermarking framework…

Statistical watermarking is a common approach for verifying whether text was written by a language model. Most existing schemes assume autoregressive generation, where tokens are produced left to right and contextual hashing is well…

With the rise of large language models (LLMs) and concerns about potential misuse, watermarks for generative LLMs have recently attracted much attention. An important aspect of such watermarks is the trade-off between their identifiability…

We consider the emerging problem of identifying the presence and use of watermarking schemes in widely used, publicly hosted, closed source large language models (LLMs). We introduce a suite of baseline algorithms for identifying watermarks…